changeset 44261:04a3ae7aba14

chg: force-set LC_CTYPE on server start to actual value from the environment

Python 3.7+ will "coerce" the LC_CTYPE variable in many instances, and this can
cause issues with chg being able to start up. D7550 attempted to fix this, but a
combination of a misreading of the way that python3.7 does the coercion and an
untested state (LC_CTYPE being set to an invalid value) meant that this was
still not quite working.

This change will cause differences between chg and hg: hg will have the LC_CTYPE
environment variable coerced, while chg will not. This is unlikely to cause any
detectable behavior differences in what Mercurial itself outputs, but it does
have two known effects:

-   When using hg, the coerced LC_CTYPE will be passed to subprocesses, even
    non-python ones. Using chg will remove the coercion, and this will not
    happen. This is arguably more correct behavior on chg's part.
-   On macOS, if you set your region to Brazil but your language to English,
    this isn't representable in locale strings, so macOS sets LC_CTYPE=UTF-8. If
    this value is passed along when ssh'ing to a non-macOS machine, some
    functions (such as locale.setlocale()) may raise an exception due to an
    unsupported locale setting. This is most easily encountered when doing an
    interactive commit/split/etc. when using ui.interface=curses.

Differential Revision: https://phab.mercurial-scm.org/D8039

--- a/contrib/chg/chg.c	Mon Feb 03 09:00:05 2020 +0100
+++ b/contrib/chg/chg.c	Wed Jan 29 13:39:50 2020 -0800
@@ -226,6 +226,16 @@
 	}
 	argv[argsize - 1] = NULL;
 
+	const char *lc_ctype_env = getenv("LC_CTYPE");
+	if (lc_ctype_env == NULL) {
+		if (putenv("CHG_CLEAR_LC_CTYPE=") != 0)
+			abortmsgerrno("failed to putenv CHG_CLEAR_LC_CTYPE");
+	} else {
+		if (setenv("CHGORIG_LC_CTYPE", lc_ctype_env, 1) != 0) {
+			abortmsgerrno("failed to setenv CHGORIG_LC_CTYYPE");
+		}
+	}
+
 	if (putenv("CHGINTERNALMARK=") != 0)
 		abortmsgerrno("failed to putenv");
 	if (execvp(hgcmd, (char **)argv) < 0)

--- a/mercurial/chgserver.py	Mon Feb 03 09:00:05 2020 +0100
+++ b/mercurial/chgserver.py	Wed Jan 29 13:39:50 2020 -0800
@@ -550,40 +550,6 @@
             raise ValueError(b'unexpected value in setenv request')
         self.ui.log(b'chgserver', b'setenv: %r\n', sorted(newenv.keys()))
 
-        # Python3 has some logic to "coerce" the C locale to a UTF-8 capable
-        # one, and it sets LC_CTYPE in the environment to C.UTF-8 if none of
-        # 'LC_CTYPE', 'LC_ALL' or 'LANG' are set (to any value). This can be
-        # disabled with PYTHONCOERCECLOCALE=0 in the environment.
-        #
-        # When fromui is called via _inithashstate, python has already set
-        # this, so that's in the environment right when we start up the hg
-        # process. Then chg will call us and tell us to set the environment to
-        # the one it has; this might NOT have LC_CTYPE, so we'll need to
-        # carry-forward the LC_CTYPE that was coerced in these situations.
-        #
-        # If this is not handled, we will fail config+env validation and fail
-        # to start chg. If this is just ignored instead of carried forward, we
-        # may have different behavior between chg and non-chg.
-        if pycompat.ispy3:
-            # Rename for wordwrapping purposes
-            oldenv = encoding.environ
-            if not any(
-                e.get(b'PYTHONCOERCECLOCALE') == b'0' for e in [oldenv, newenv]
-            ):
-                keys = [b'LC_CTYPE', b'LC_ALL', b'LANG']
-                old_keys = [k for k, v in oldenv.items() if k in keys and v]
-                new_keys = [k for k, v in newenv.items() if k in keys and v]
-                # If the user's environment (from chg) doesn't have ANY of the
-                # keys that python looks for, and the environment (from
-                # initialization) has ONLY LC_CTYPE and it's set to C.UTF-8,
-                # carry it forward.
-                if (
-                    not new_keys
-                    and old_keys == [b'LC_CTYPE']
-                    and oldenv[b'LC_CTYPE'] == b'C.UTF-8'
-                ):
-                    newenv[b'LC_CTYPE'] = oldenv[b'LC_CTYPE']
-
         encoding.environ.clear()
         encoding.environ.update(newenv)
 
@@ -730,6 +696,16 @@
     # environ cleaner.
     if b'CHGINTERNALMARK' in encoding.environ:
         del encoding.environ[b'CHGINTERNALMARK']
+    # Python3.7+ "coerces" the LC_CTYPE environment variable to a UTF-8 one if
+    # it thinks the current value is "C". This breaks the hash computation and
+    # causes chg to restart loop.
+    if b'CHGORIG_LC_CTYPE' in encoding.environ:
+        encoding.environ[b'LC_CTYPE'] = encoding.environ[b'CHGORIG_LC_CTYPE']
+        del encoding.environ[b'CHGORIG_LC_CTYPE']
+    elif b'CHG_CLEAR_LC_CTYPE' in encoding.environ:
+        if b'LC_CTYPE' in encoding.environ:
+            del encoding.environ[b'LC_CTYPE']
+        del encoding.environ[b'CHG_CLEAR_LC_CTYPE']
 
     if repo:
         # one chgserver can serve multiple repos. drop repo information

--- a/tests/test-chg.t	Mon Feb 03 09:00:05 2020 +0100
+++ b/tests/test-chg.t	Wed Jan 29 13:39:50 2020 -0800
@@ -332,8 +332,8 @@
   YYYY/MM/DD HH:MM:SS (PID)> log -R cached
   YYYY/MM/DD HH:MM:SS (PID)> loaded repo into cache: $TESTTMP/cached (in  ...s)
 
-Test that chg works even when python "coerces" the locale (py3.7+, which is done
-by default if none of LC_ALL, LC_CTYPE, or LANG are set in the environment)
+Test that chg works (sets to the user's actual LC_CTYPE) even when python
+"coerces" the locale (py3.7+)
 
   $ cat > $TESTTMP/debugenv.py <<EOF
   > from mercurial import encoding
@@ -347,9 +347,22 @@
   >         if v is not None:
   >             ui.write(b'%s=%s\n' % (k, encoding.environ[k]))
   > EOF
+(hg keeps python's modified LC_CTYPE, chg doesn't)
+  $ (unset LC_ALL; unset LANG; LC_CTYPE= "$CHGHG" \
+  >    --config extensions.debugenv=$TESTTMP/debugenv.py debugenv)
+  LC_CTYPE=C.UTF-8 (py37 !)
+  LC_CTYPE= (no-py37 !)
+  $ (unset LC_ALL; unset LANG; LC_CTYPE= chg \
+  >    --config extensions.debugenv=$TESTTMP/debugenv.py debugenv)
+  LC_CTYPE=
+  $ (unset LC_ALL; unset LANG; LC_CTYPE=unsupported_value chg \
+  >    --config extensions.debugenv=$TESTTMP/debugenv.py debugenv)
+  LC_CTYPE=unsupported_value
+  $ (unset LC_ALL; unset LANG; LC_CTYPE= chg \
+  >    --config extensions.debugenv=$TESTTMP/debugenv.py debugenv)
+  LC_CTYPE=
   $ LANG= LC_ALL= LC_CTYPE= chg \
   >    --config extensions.debugenv=$TESTTMP/debugenv.py debugenv
   LC_ALL=
-  LC_CTYPE=C.UTF-8 (py37 !)
-  LC_CTYPE= (no-py37 !)
+  LC_CTYPE=
   LANG=